Flow Vector Prediction Using EM Algorithms

Abstract

This paper considers the problem of predicting the number, length and distribution of IP traffic flows some time into the future, based upon packets collected in the present. Two versions of the Expectation-Maximization (EM) algorithm are used to predict the mean flow length and complete flow distributions for subsequent timesteps. A model is first used to represent the histogram of flows corresponding to any given time interval, and the EM algorithms are then used to estimate the parameters of the model. The proposed algorithms are tested on a large number of commonly-available data traces and both show high prediction accuracy.